huggingtweets/minidiscplus

The model is based on a pre-trained GPT-2 which is fine-tuned on @minidiscplus's tweets . The data is tracked with W&B artifacts at every step of the pipeline . You can use this model directly with a pipeline for text generation: pipeline('text-generation', model('My dream is) model="Huggingtweets/Minidisc+') model="My dream is", num_return_sequences=5" Model was trained on the same limitations and bias as GPT 2 . The model has been created by Boris Dayma and is now available to create your own bot based on your favorite user with the demo,